@@ -725,6 +725,41 @@ DEF_HELPER_FLAGS_5(gvec_rsqrts_s, TCG_CALL_NO_RWG,
DEF_HELPER_FLAGS_5(gvec_rsqrts_d, TCG_CALL_NO_RWG,
void, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(sve_faddv_h, TCG_CALL_NO_RWG,
+ i64, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(sve_faddv_s, TCG_CALL_NO_RWG,
+ i64, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(sve_faddv_d, TCG_CALL_NO_RWG,
+ i64, ptr, ptr, ptr, i32)
+
+DEF_HELPER_FLAGS_4(sve_fmaxnmv_h, TCG_CALL_NO_RWG,
+ i64, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(sve_fmaxnmv_s, TCG_CALL_NO_RWG,
+ i64, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(sve_fmaxnmv_d, TCG_CALL_NO_RWG,
+ i64, ptr, ptr, ptr, i32)
+
+DEF_HELPER_FLAGS_4(sve_fminnmv_h, TCG_CALL_NO_RWG,
+ i64, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(sve_fminnmv_s, TCG_CALL_NO_RWG,
+ i64, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(sve_fminnmv_d, TCG_CALL_NO_RWG,
+ i64, ptr, ptr, ptr, i32)
+
+DEF_HELPER_FLAGS_4(sve_fmaxv_h, TCG_CALL_NO_RWG,
+ i64, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(sve_fmaxv_s, TCG_CALL_NO_RWG,
+ i64, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(sve_fmaxv_d, TCG_CALL_NO_RWG,
+ i64, ptr, ptr, ptr, i32)
+
+DEF_HELPER_FLAGS_4(sve_fminv_h, TCG_CALL_NO_RWG,
+ i64, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(sve_fminv_s, TCG_CALL_NO_RWG,
+ i64, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(sve_fminv_d, TCG_CALL_NO_RWG,
+ i64, ptr, ptr, ptr, i32)
+
DEF_HELPER_FLAGS_5(sve_fadda_h, TCG_CALL_NO_RWG,
i64, i64, ptr, ptr, ptr, i32)
DEF_HELPER_FLAGS_5(sve_fadda_s, TCG_CALL_NO_RWG,
@@ -2832,6 +2832,67 @@ uint32_t HELPER(sve_while)(void *vd, uint32_t count, uint32_t pred_desc)
return predtest_ones(d, oprsz, esz_mask);
}
+/* Recursive reduction on a function;
+ * C.f. the ARM ARM function ReducePredicated.
+ *
+ * While it would be possible to write this without the DATA temporary,
+ * it is much simpler to process the predicate register this way.
+ * The recursion is bounded to depth 7 (128 fp16 elements), so there's
+ * little to gain with a more complex non-recursive form.
+ */
+#define DO_REDUCE(NAME, TYPE, H, FUNC, IDENT) \
+static TYPE NAME##_reduce(TYPE *data, float_status *status, uintptr_t n) \
+{ \
+ if (n == 1) { \
+ return *data; \
+ } else { \
+ uintptr_t half = n / 2; \
+ TYPE lo = NAME##_reduce(data, status, half); \
+ TYPE hi = NAME##_reduce(data + half, status, half); \
+ return TYPE##_##FUNC(lo, hi, status); \
+ } \
+} \
+uint64_t HELPER(NAME)(void *vn, void *vg, void *vs, uint32_t desc) \
+{ \
+ uintptr_t i, oprsz = simd_oprsz(desc), maxsz = simd_maxsz(desc); \
+ TYPE data[sizeof(ARMVectorReg) / sizeof(TYPE)]; \
+ for (i = 0; i < oprsz; ) { \
+ uint16_t pg = *(uint16_t *)(vg + H1_2(i >> 3)); \
+ do { \
+ TYPE nn = *(TYPE *)(vn + H(i)); \
+ *(TYPE *)((void *)data + i) = (pg & 1 ? nn : IDENT); \
+ i += sizeof(TYPE), pg >>= sizeof(TYPE); \
+ } while (i & 15); \
+ } \
+ for (; i < maxsz; i += sizeof(TYPE)) { \
+ *(TYPE *)((void *)data + i) = IDENT; \
+ } \
+ return NAME##_reduce(data, vs, maxsz / sizeof(TYPE)); \
+}
+
+DO_REDUCE(sve_faddv_h, float16, H1_2, add, float16_zero)
+DO_REDUCE(sve_faddv_s, float32, H1_4, add, float32_zero)
+DO_REDUCE(sve_faddv_d, float64, , add, float64_zero)
+
+/* Identity is floatN_default_nan, without the function call. */
+DO_REDUCE(sve_fminnmv_h, float16, H1_2, minnum, 0x7E00)
+DO_REDUCE(sve_fminnmv_s, float32, H1_4, minnum, 0x7FC00000)
+DO_REDUCE(sve_fminnmv_d, float64, , minnum, 0x7FF8000000000000ULL)
+
+DO_REDUCE(sve_fmaxnmv_h, float16, H1_2, maxnum, 0x7E00)
+DO_REDUCE(sve_fmaxnmv_s, float32, H1_4, maxnum, 0x7FC00000)
+DO_REDUCE(sve_fmaxnmv_d, float64, , maxnum, 0x7FF8000000000000ULL)
+
+DO_REDUCE(sve_fminv_h, float16, H1_2, min, float16_infinity)
+DO_REDUCE(sve_fminv_s, float32, H1_4, min, float32_infinity)
+DO_REDUCE(sve_fminv_d, float64, , min, float64_infinity)
+
+DO_REDUCE(sve_fmaxv_h, float16, H1_2, max, float16_chs(float16_infinity))
+DO_REDUCE(sve_fmaxv_s, float32, H1_4, max, float32_chs(float32_infinity))
+DO_REDUCE(sve_fmaxv_d, float64, , max, float64_chs(float64_infinity))
+
+#undef DO_REDUCE
+
uint64_t HELPER(sve_fadda_h)(uint64_t nn, void *vm, void *vg,
void *status, uint32_t desc)
{
@@ -3180,6 +3180,61 @@ static void trans_FMUL_zzx(DisasContext *s, arg_FMUL_zzx *a, uint32_t insn)
tcg_temp_free_ptr(status);
}
+/*
+ *** SVE Floating Point Fast Reduction Group
+ */
+
+typedef void gen_helper_fp_reduce(TCGv_i64, TCGv_ptr, TCGv_ptr,
+ TCGv_ptr, TCGv_i32);
+
+static void do_reduce(DisasContext *s, arg_rpr_esz *a,
+ gen_helper_fp_reduce *fn)
+{
+ unsigned vsz = vec_full_reg_size(s);
+ unsigned p2vsz = pow2ceil(vsz);
+ TCGv_i32 t_desc = tcg_const_i32(simd_desc(vsz, p2vsz, 0));
+ TCGv_ptr t_zn, t_pg, status;
+ TCGv_i64 temp;
+
+ temp = tcg_temp_new_i64();
+ t_zn = tcg_temp_new_ptr();
+ t_pg = tcg_temp_new_ptr();
+
+ tcg_gen_addi_ptr(t_zn, cpu_env, vec_full_reg_offset(s, a->rn));
+ tcg_gen_addi_ptr(t_pg, cpu_env, pred_full_reg_offset(s, a->pg));
+ status = get_fpstatus_ptr(a->esz == MO_16);
+
+ fn(temp, t_zn, t_pg, status, t_desc);
+ tcg_temp_free_ptr(t_zn);
+ tcg_temp_free_ptr(t_pg);
+ tcg_temp_free_ptr(status);
+ tcg_temp_free_i32(t_desc);
+
+ write_fp_dreg(s, a->rd, temp);
+ tcg_temp_free_i64(temp);
+}
+
+#define DO_VPZ(NAME, name) \
+static void trans_##NAME(DisasContext *s, arg_rpr_esz *a, uint32_t insn) \
+{ \
+ static gen_helper_fp_reduce * const fns[3] = { \
+ gen_helper_sve_##name##_h, \
+ gen_helper_sve_##name##_s, \
+ gen_helper_sve_##name##_d, \
+ }; \
+ if (a->esz == 0) { \
+ unallocated_encoding(s); \
+ return; \
+ } \
+ do_reduce(s, a, fns[a->esz - 1]); \
+}
+
+DO_VPZ(FADDV, faddv)
+DO_VPZ(FMINNMV, fminnmv)
+DO_VPZ(FMAXNMV, fmaxnmv)
+DO_VPZ(FMINV, fminv)
+DO_VPZ(FMAXV, fmaxv)
+
/*
*** SVE Floating Point Accumulating Reduction Group
*/
@@ -739,6 +739,14 @@ FMUL_zzx 01100100 0.1 .. rm:3 001000 rn:5 rd:5 \
FMUL_zzx 01100100 101 index:2 rm:3 001000 rn:5 rd:5 esz=2
FMUL_zzx 01100100 111 index:1 rm:4 001000 rn:5 rd:5 esz=3
+### SVE FP Fast Reduction Group
+
+FADDV 01100101 .. 000 000 001 ... ..... ..... @rd_pg_rn
+FMAXNMV 01100101 .. 000 100 001 ... ..... ..... @rd_pg_rn
+FMINNMV 01100101 .. 000 101 001 ... ..... ..... @rd_pg_rn
+FMAXV 01100101 .. 000 110 001 ... ..... ..... @rd_pg_rn
+FMINV 01100101 .. 000 111 001 ... ..... ..... @rd_pg_rn
+
### SVE FP Accumulating Reduction Group
# SVE floating-point serial reduction (predicated)
Signed-off-by: Richard Henderson <richard.henderson@linaro.org> --- target/arm/helper-sve.h | 35 ++++++++++++++++++++++++++ target/arm/sve_helper.c | 61 ++++++++++++++++++++++++++++++++++++++++++++++ target/arm/translate-sve.c | 55 +++++++++++++++++++++++++++++++++++++++++ target/arm/sve.decode | 8 ++++++ 4 files changed, 159 insertions(+) -- 2.14.3